EP3987480B1 - Bildbasierte fehlerdetektionen in der generativen fertigung - Google Patents

Bildbasierte fehlerdetektionen in der generativen fertigung

Info

Publication number
EP3987480B1
EP3987480B1 EP19758533.4A EP19758533A EP3987480B1 EP 3987480 B1 EP3987480 B1 EP 3987480B1 EP 19758533 A EP19758533 A EP 19758533A EP 3987480 B1 EP3987480 B1 EP 3987480B1
Authority
EP
European Patent Office
Prior art keywords
image
given layer
hatch
built
tracking
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP19758533.4A
Other languages
English (en)
French (fr)
Other versions
EP3987480C0 (de
EP3987480A1 (de
Inventor
Gaurav AMETA
Suraj Ravi MUSUVATHY
Elena Arvanitis
David Madeley
Omar FERGANI
Tom Van 't Erve
Livio Dalloro
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens Industry Software Inc
Original Assignee
Siemens Industry Software Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens Industry Software Inc filed Critical Siemens Industry Software Inc
Publication of EP3987480A1 publication Critical patent/EP3987480A1/de
Application granted granted Critical
Publication of EP3987480B1 publication Critical patent/EP3987480B1/de
Publication of EP3987480C0 publication Critical patent/EP3987480C0/de
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
    • B22F10/30—Process control
    • B22F10/36—Process control of energy beam parameters
    • B22F10/366—Scanning parameters, e.g. hatch distance or scanning strategy
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
    • B22F10/30—Process control
    • B22F10/38—Process control to achieve specific product aspects, e.g. surface smoothness, density, porosity or hollow structures
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
    • B22F10/80—Data acquisition or data processing
    • B22F10/85—Data acquisition or data processing for controlling or regulating additive manufacturing processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F12/00—Apparatus or devices specially adapted for additive manufacturing; Auxiliary means for additive manufacturing; Combinations of additive manufacturing apparatus or devices with other processing apparatus or devices
    • B22F12/90—Means for process control, e.g. cameras or sensors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
    • B29C64/10—Processes of additive manufacturing
    • B29C64/141—Processes of additive manufacturing using only solid materials
    • B29C64/153—Processes of additive manufacturing using only solid materials using layers of powder being selectively joined, e.g. by selective laser sintering or melting
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
    • B29C64/30—Auxiliary operations or equipment
    • B29C64/386—Data acquisition or data processing for additive manufacturing
    • B29C64/393—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y10/00—Processes of additive manufacturing
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y50/00—Data acquisition or data processing for additive manufacturing
    • B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
    • B22F10/20—Direct sintering or melting
    • B22F10/28—Powder bed fusion, e.g. selective laser melting [SLM] or electron beam melting [EBM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/10—Additive manufacturing, e.g. three-dimensional [3D] printing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20108—Interactive selection of 2D slice in a 3D data set
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30116—Casting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30144—Printing quality
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/25—Process efficiency

Definitions

  • Computer systems can be used to create, use, and manage data for products and other items.
  • Examples of computer systems include computer-aided design (CAD) systems (which may include computer-aided engineering (CAE) systems), computer-aided manufacturing (CAM) systems, visualization systems, product data management (PDM) systems, product lifecycle management (PLM) systems, and more.
  • CAD computer-aided design
  • CAE computer-aided engineering
  • CAM computer-aided manufacturing
  • PDM product data management
  • PLM product lifecycle management
  • WO 2017/141070 A1 discloses a computer-implemented method for virtualization of rapid prototyping processes which allows a user to envisage accurately a manufacturing operation and final product output to be had.
  • Additive manufacturing may be performed through use of 3D printers that construct objects.
  • Some forms of additive manufacturing is laser powder bed fusion, in which a laser can be used as a power source to sinter/melt powdered material (e.g., metal powder) laid up on a powder bed or build platform. As successive layers of metal powder are added to the powder bed and sintered by the laser, a product is additively manufactured in a layer-by-layer manner.
  • Various additive manufacturing techniques use application of a heat or energy source on powder beds to additively construct an object, including laser powder bed fusion, selective laser melting (SLM), selective laser sintering (SLS), electron beam melting (EBM), and more.
  • SLM selective laser melting
  • SLS selective laser sintering
  • EBM electron beam melting
  • energy-based processes may refer to any additive manufacturing processes that applies an energy source (e.g., laser or electron beam) to melt powder laid up on a powder bed or build platform (e.g., in contrast to deposition-based additive manufacturing processes that deposit already-melted material in the form of beads).
  • an energy source e.g., laser or electron beam
  • a digital 3-dimensional (3D) geometry of part can be sliced into 2-dimensional (2D) layers by a CAM system or 3D printing system to guide physical manufacture of the part.
  • These digitally sliced layers may include slice contours that define boundaries of the part.
  • laser/electron beam pathing to sinter layers of metal powder may be computed for each layer, and any such energy pathing (e.g., a laser toolpath) may be referred to herein as hatch tracking, hatch tracks, or hatch patterning.
  • Hatch tracks may be computed from the slice contours of 2D layers, and may represent energy pathing (whether laser-based, electron-based, etc.) within the slice contours to sinter metal powder in order to physically construct each respective layer.
  • Such hatch tracking may be limited in form to parallel vectors or other predetermined patterns, angled paths, or shapes.
  • computed hatch tracking by CAM systems or build processors may be incapable of completely covering a slice contour.
  • computational errors during hatch tracking determinations may result in missing vectors within the slice contour, causing incomplete formation of a given layer during sintering or material deposition. Accordingly, part gaps, improperly fused metal powder, or other part defects may occur during physical part construction using incomplete or erroneous hatch trackings.
  • the disclosure herein provides systems, methods, devices, and logic for image-based defect detections in additive manufacturing as defined in the appended claims.
  • the image-based defect detection features disclosed herein include rendering multiple digital images for sliced layers of a 3D geometry, including an as-built image based on rendering the hatch tracking determined for slice contours of a given layer as well as an idealized image constructed from the slice contours. Via image analysis, differences between the as-built and idealized images are determined, whichcorrelate to physical defects that be introduced to a part during physical manufacture of a given part layer.
  • the image-based defect detection features described herein support gap and defect detection prior to physical manufacture, which thus support defect analysis and correction without needless expending physical resources to construct defective parts.
  • the image-based defect detection features described herein thus provide manufacturing validations for 3D parts prior to physical construction and may increase the accuracy and efficiency at which 3D parts are constructed via additive manufacturing.
  • FIG. 1 shows an example of a computing system 100 that supports image-based defect detections in additive manufacturing.
  • the computing system 100 may take the form of a single or multiple computing devices such as application servers, compute nodes, desktop or laptop computers, smart phones or other mobile devices, tablet devices, embedded controllers, and more.
  • the computing system 100 is part of or implements (at least in part) a CAM system or a 3D printing system, which may include a build processor.
  • the computing system 100 may support various 3D printing operations such as 3D object slicing, manufacturing validations, and the like, in order to support additive manufacture of parts.
  • the computing system 100 shown in Figure 1 includes an access engine 108 and a defect detection engine 110.
  • the computing system 100 may implement the engines 108 and 110 (including components thereof) in various ways, for example as hardware and programming.
  • the programming for the engines 108 and 110 may take the form of processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the engines 108 and 110 may include a processor to execute those instructions.
  • a processor may take the form of single processor or multiprocessor systems, and in some examples, the computing system 100 implements multiple engines using the same computing system features or hardware components (e.g., a common processor or a common storage medium).
  • the access engine 108 accesses a slice contour of a given layer of a 3D object designed for manufacture through an additive manufacturing process as well as obtain hatch tracking for the slice contour.
  • the hatch tracking is representative of an energy path to melt (e.g., sinter) metal powder for constructing the given layer through the additive manufacturing process.
  • the defect detection engine 110 constructs, from the slice contour, an as-built image for the given layer by rendering the hatch tracking in the slice contour and construct, from the slice contour, an idealized image for the given layer.
  • the defect detection engine 110 further identifies defects in the given layer via image analysis between the as-built image and the idealized image.
  • image-based defect detection features are described in greater detail next. Many of the examples described herein using laser-based paths to melt or sinter powdered metal on a powder bed as an illustrative example. However, the image-based defect detection features described herein may be consistently applied for any energy-based additive manufacturing techniques that use hatch tracking for energy toolpaths (to path an electron beam instead of a laser).
  • FIG. 2 shows examples of image-based defect detections that a computing system may perform for a 3D object model.
  • a computing system is illustrated in the form of an access engine 108 and a defect detection engine 110.
  • access engine 108 and a defect detection engine 110.
  • other system implementations are contemplated herein.
  • the access engine 108 accesses slice data for a part design.
  • the part design may take the form of a 3D geometry, such as the 3D object model 210 shown in Figure 2 .
  • the 3D object model 210 may take the form of any suitable CAD format or CAD file, and may represent a 3D shape (e.g., geometry) of the part.
  • the access engine 108 accesses slice data 220 for the 3D object model 210, which may include slice contours and hatch tracking for any number of sliced layers of the 3D object model 210.
  • slice data 220 may be computed by a build processor of a 3D printing system or any suitable CAM system.
  • the slice data 220 may take the form of 2D layers sliced from the 3D object model 210 for 3D printing of the part design represented by the 3D object model 210.
  • Slice data 220 for each given layer e.g., each given slice of the slice data 220
  • the access engine 108 may retrieve, load, or otherwise access computed slice data 220 from CAM systems, build processors, or data structures used to store such slice data 220.
  • a build processor or CAM system may compute hatch tracking for layers of the 3D object model 210, and the hatch tracking may represent a determined laser path (for laser powder bed fusions) or electron beam path (for EBM processes) to physically construct the given layer via additive manufacturing.
  • the access engine 108 obtains hatch tracking computed for the various layers of the 3D object model 210.
  • slice contours and hatch tracking for an example layer in the slice data 220 are illustrated as the slice contour 231 and the hatch tracking 232.
  • Hatch tracking computations may be limited to specific forms, structures, or parameters imposed by CAM systems or build processors to guide pathing of a laser or other energy application tool. For instance, hatch tracking computed for a given layer may be limited in form to parallel vectors, predetermined shapes or angles, or other toolpath parameters that reduce the degree to which the computed hatch tracking can cover a free-form shape. Computation errors by a build processor or CAM system may also result in hatching errors, such as missing vectors, that also reduce coverage of pathing within the slice contour of a given layer.
  • the defect detection engine 110 analyzes slice data 220 of the 3D object model 210.
  • the defect detection engine 110 constructs as-built and idealized images for sliced layers of a part design from accessed slice data 220.
  • An as-built image constructed by the defect detection engine 110 in effect, represents a simulation of a build of a given layer by rendering (e.g., coloring) hatch tracking computed for the given layer to represent sintered metal powder formed for the given layer.
  • An idealized image for the given layer represents a complete or perfect construction of the given layer, e.g., without any gaps, defects, or manufacture imperfections resulting from inaccurate or incomplete hatch tracking for the given layer.
  • the defect detection engine 110 may create an image representation of the slice contour(s) of the given layer.
  • slice data 220 generated by a CAM system or build processor may include a slice contour 231 for a given layer, which the defect detection engine 110 may capture in any suitable image format (e.g., .jpg, .png, bitmaps, any CAD or CAM-based image representations, and the like).
  • the defect detection engine 110 renders the hatch tracking 232 for the given layer to construct the as-built image. That is, the defect detection engine 110 may color the hatch tracking 232 in the digital image to represent a simulated coverage of laser or electron beam-based sintering during physical manufacture of the given layer.
  • Rendering of the hatch tracking 232 for a given layer may be performed in various ways by the defect detection engine 110.
  • the defect detection engine 110 renders the hatch tracking 232 at a constant color width as specified by a melt pool width parameter for the additive manufacturing process.
  • the melt pool width parameter may be a configurable parameter, e.g., as specified by a user for use in defect detection rendering of the hatch tracking 232 (e.g., at constant value of 100 or 150 micrometers for rendering the hatch tracking 232).
  • the defect detection engine 110 may color over portions of a slice contour digital image along the hatch tracking 232 at a constant color (e.g., pixel) width, doing so in accordance with the specified melt pool width.
  • the defect detection engine 110 may apply a fixed color (e.g., white) at a fixed pixel width (e.g., 5 pixels) along the hatch tracking computed for a given layer.
  • the defect detection engine 110 overlay or render a line with the constant pixel width over the hatch tracking for a given layer at a particular alignment with the hatch tracking (e.g., centered on the hatch tracking, with the hatch tracking aligned at the left or right of the rendered line, or at a preconfigured pixel offset with respect to the hatch tracking).
  • Such a rendering implementation via a constant color width may increase the speed at which as-built images are constructed by allowing rendering of hatch tracking to be performed with simpler coloring operations and increased speed.
  • As-build image rendering at increased speeds is particularly useful as the hatch trackings computed for a given layer may number into the millions (or more), and more complex rendering operations or simulations may result in increased (and possibly unacceptable or non-practical) processing times.
  • the defect detection engine 110 renders the hatch tracking 232 for a given layer at a variable color width according to a statistical function that models a melt pool width of an additive manufacturing process.
  • the statistical function may compute a melt powder width at different portions of the given layer based at least on laser power, laser speed, and metal powder characteristics to be used in the additive manufacturing process.
  • the statistical function may instead account for energy parameters and characteristics of these processes instead, such as electron beam intensities, speed, etc. Any such characteristics and any other parameters of the additive manufacturing processes may be configurable, and the statistical function may account for such parameters in determining a melt pool width for coloring the hatch tracking 232 at various points in the given layer.
  • This example rendering implementation via a statistical function may increase the accuracy at which a given layer is simulated and represented as the as-built image, which may allow for finer defect detection capabilities at increased granularity and accuracy.
  • the defect detection engine 110 renders the as-built image at an image resolution capable to visualize sintering or deposition gaps of a threshold size.
  • the defect detection engine 110 renders the as-built image at a predetermined resolution (e.g., 100,000 x 100,000 pixels) such that gaps of a threshold size are visualized in the as-built image.
  • defect detection engine 110 may determine an image resolution for the as-built image at a configurable or predetermined physical size-to-pixel ratio, e.g. at a 2 micrometer 2 -per-pixel ratio.
  • the physical size of the 3D object model 210 may control the image resolution at which the defect detection engine 110 constructs the as-built image.
  • the defect detection engine 110 may determine an image resolution for the as-built image based on a predetermined pixel width for the melt pool width parameter. To illustrate, the defect detection engine 110 may assign a pixel width of 50 pixels to a constant melt pool width parameter (and thus a 100 micrometer width pool parameter will result in a determined image resolution of 0.5 micrometer-per-pixel width ratio).
  • a configurable parameter may specify a minimum acceptable gap width (e.g., 0.5 micrometers), and the defect detection engine 110 may determine an image resolution for the as-built image such that any gaps greater in size than the minimum acceptable gap width are visualized in the as-built image (e.g., at a 0.45 micrometer-per-pixel width ratio, ensuring that gaps at the minimum acceptable gap width of 0.5 micrometers are visualized by at least 1 image pixel).
  • a minimum acceptable gap width e.g., 0.5 micrometers
  • the defect detection engine 110 may determine an image resolution for the as-built image such that any gaps greater in size than the minimum acceptable gap width are visualized in the as-built image (e.g., at a 0.45 micrometer-per-pixel width ratio, ensuring that gaps at the minimum acceptable gap width of 0.5 micrometers are visualized by at least 1 image pixel).
  • construction of the as-built image by the defect detection engine 110 may be computationally expensive.
  • the defect detection engine 110 may utilize parallel computing to support construction of the as-built image with increased speed.
  • the computed hatch tracking 232 may number in the millions of vectors (or more), and the defect detection engine 110 may leverage multi-threading capabilities of multi-central processing unit (CPU) systems or multi-graphical processing unit (GPU) systems to decrease overall computational latency in generating as-built images for a given layer of a 3D geometry.
  • CPU central processing unit
  • GPU multi-graphical processing unit
  • the defect detection engine 110 supports construction of an as-built image for a given layer of the 3D object model 210.
  • the defect detection engine 110 also constructs an idealized image of a given layer. To do so, the defect detection engine 110 captures the slice contour 231 of the given layer in a suitable image format and color the image to represent an ideal build of the given layer. In particular, the defect detection engine 110 constructs the idealized image for the given layer by completely coloring the interior of the slice contour 231, e.g., via a flood fill operation to color the image. A complete coloring represents an idealized build in that the given layer is entirely sintered/constructed within the part boundary represented by the slice contour 231 of the given layer.
  • the defect detection engine 110 constructs the idealized image of the given layer at an identical image resolution as the as-built image for the given layer, and do so in a manner such that the slice contour 231 is consistently positioned and aligned (e.g., at identical image locations) for both the as-built image and idealized image.
  • the defect detection engine 110 constructs an as-built image and an idealized image for a given layer of a 3D geometry. Examples of such images are respectively depicted in Figure 2 as the as-built image 240 and idealized image 250.
  • the slice contour 231 and the hatch tracking 232 for a given layer are rendered (e.g., colored) in black by the defect detection engine 110 to represent a physical build of the given layer via the computed hatch tracking 232.
  • Non-black (e.g., white) portions of the as-built image 240 indicate portions of the given layer that the hatch tracking 232 fails to cover, and which may result in gaps or defects during layer construction.
  • the idealized image 250 is flood filled with a black coloring within the slice contour 231 by the defect detection engine 110, which may represent an ideal construction of the given layer without any gaps or defects.
  • the defect detection engine 110 may perform an image analysis between the as-built image 240 and the idealized image 250 for a given layer to identify build defects that may result during physical manufacture. As the defect detection engine 110 renders the as-built image 240 and the idealized image 250 with aligned contour positioning and image resolutions, an image difference operation may be performed to identify discrepancies between the constructed images. Image difference operations may, for example, subtract pixel color values between images to identify areas that differentiated regions between the images.
  • image analysis results 260 are shown in Figure 2 , which the defect detection engine 110 may compute or determine based on performed image difference operations between the as-built image 240 and idealized image 250.
  • image analysis results 260 sinter or deposition gaps present in the as-built image 240 as illustrated in white coloring, which may result from missing or incomplete vector hatching paths in the hatch tracking 232.
  • the defect detection engine 110 identifies gaps and defects that may be introduced during physical manufacture of a given layer of the 3D object model 210.
  • the defect detection engine 110 may further analyze the image analysis results 260 to determine defect characteristics for the given layer. For instance, the defect detection engine 110 identifies a number of pixels, size, width, length, or other image characteristics from the image analysis results 260 for the defects (e.g., gaps colored in white). Based on the image analysis results 260 and image resolution, the defect detection engine 110 may compute defect characteristics in physical measures (e.g., instead of pixels), including a gap count numbering the amount of detected gaps, gap ranges identifying a number of gaps within various size ranges, gap statistics such as a maximum, minimum, or average size of gaps for a given layer, a gap percentage of the given layer (can also be referred to as a deficiency percentage), and more.
  • defect characteristics in physical measures (e.g., instead of pixels), including a gap count numbering the amount of detected gaps, gap ranges identifying a number of gaps within various size ranges, gap statistics such as a maximum, minimum, or average size of gaps for a given layer, a gap percentage of
  • Visual tools such as graphs, charts, and histograms may be utilized by the defect detection engine 110 to present gap or defect analysis results to a user via a user interface.
  • Tables 1, 2, and 3 below provide illustrative examples of defect statistics that the defect detection engine 110 may compute or present to a user, whether for a particular layer (e.g., Table 1) or for multiple layers (e.g., Tables 2 and 3).
  • Table 1 Example computed gap size ranges for a given layer of a 3D object model Layer 9 Range (micrometers 2 ) Frequency (Number) 0.000 - 0.125 295 0.125-0.250 4 0.250-0.375 4 0.375-0.500 0 0.500-0.625 2 0.625-0.750 1 Table 2 - Example computed gap statistics for multiple layers of a 3D object model Layer Gap Count Average Area Min Gap Area Max Gap Area 1 320 0.02956543 0.000313 0.665313 2 449 0.01559779 0.000313 0.456563 3 349 0.02250716 0.000313 0.486875 4 384 0.02059244 0.000313 0.611563 5 317 0.02994479 0.000313 1.098752 6 471 0.01592360 0.000313 0.469588 Table 3 - Example computed deficiency percentages for multiple layers of a 3D object model based on different melt pool width parameters used to construct as-built images Melt Pool Width Layer
  • the defect detection engine 110 may compute various defect statistics and visualize the computed defect statistics in any number of ways.
  • the defect detection engine 110 constructs multiple as-built images for the same layer of a 3D geometry. In doing so, the defect detection engine 110 renders the different as-built images with different rendering parameters. As one example, the defect detection engine 110 renders as-built images with different melt pool width parameters used to apply a constant color width along the hatch tracking 232 for the given layer.
  • Doing so may support analysis and comparison on the effect of melt pool width on the construction of a given layer, e.g., by computing and comparing gap statistics for multiple as-built images rendered with different melt pool widths (e.g., a first as-built image rendered with a 100 micrometer melt pool width and a second as-built image rendered with a 150 micrometer melt pool width, both of which are used in image analyses with an idealized image for the given layer).
  • gap statistics for multiple as-built images rendered with different melt pool widths e.g., a first as-built image rendered with a 100 micrometer melt pool width and a second as-built image rendered with a 150 micrometer melt pool width, both of which are used in image analyses with an idealized image for the given layer.
  • An example of such analysis through multiple as-built images is shown above in Table 3.
  • the defect detection engine 110 constructs an as-built image for a given layer by accounting for multiple other layers in the 3D object model 210.
  • the defect detection engine 110 may account for thermal energy impacts from physicals construction of layers on top of (physically above along a build axis) a given layer of a manufactured part.
  • thermal energy e.g., from a laser or electron beam
  • layer 'i' may impact layer 'i' as well, and this thermal energy may be applicable or observed for 'k' number of layers, e.g., layer 'i' is affected by layer 'i+1', layer 'i+2', ... and so forth through layer 'i+k'.
  • This parameter 'k' may be referred to as an additional layer parameter, which may be configurable by the defect detection engine 110 and which may control the extent to which the defect detection engine 110 accounts for additional layers in constructing the as-built image for a given layer 'i'.
  • the defect detection engine 110 constructs the as-built image for layer 'i' by also rendering as-built images for 'k' additional layers, particular layers 'i+1' (directly above layer 'i'), 'i+2' (two layers above layer 'i'), and so on up through layer 'i+k' ('k' number of layers above layer 'i').
  • the defect detection engine 110 may aggregate the multiple as-built images into a single as-built image for layer 'i'. To do so, the defect detection engine 110 may additionally color the as-built image for layer 'i' based on the as-built images constructed for the 'k' additional layers.
  • Color contribution amounts for multiple layers may be implemented via color scaling in the as-built image constructed for a given layer 'i'.
  • the defect detection engine 110 renders the as-built image for layer 'i' as a grayscale image, with coloring of hatch tracking for layer 'i' rendered at 100% contribution (e.g., white).
  • contributions from the 'k' layers above layer 'i' are rendered by the defect detection engine in the as-built image for layer 'i' with scaling contributions based on a grayscale intensity value scaling between 100% (white value) and 0% (black value).
  • gaps present in the hatch tracking for given layer 'i' may be (at least partially) filled via contributions from the various 'k' layers above layer 'i', and the defect detection engine 110 renders an as-built image for layer 'i' by additionally accounting for 'k' number of layers above layer 'i'.
  • a threshold grayscale value e.g., 50% on the grayscale intensity value
  • the threshold value may be user-configurable.
  • an access engine 108 and defect detection engine 110 may provide image-based defect detections for part geometries to be physically constructed via additive manufacturing, such as through laser powder bed fusion, SLS, SLM, EBM, or other energy-based processes. Although some of the examples described herein are provided for a specific layer 'i', the access engine 108 and defect detection engine 110 may, in a consistent manner, support image analysis-based defect detections for some or all of the layers of a 3D object model 210.
  • image-based defect detection features described herein may provide an automated and efficient solution for defect detections prior to physical manufacture, and may be conveniently integrated as components or capabilities within a CAM system or 3D printing system (e.g., via machine-readable instructions and a build processor).
  • image-based defect detections may account for the impact of multiple different layers (e.g., up to 'k' number of additional layers), which may increase the capability and accuracy at which rendered as-built images can be compared to idealized images for gap and defect detections.
  • Identified gaps, defects, and other part layer deficiencies may be addressed and corrected, e.g., via updated hatch tracking to address or fill the identified gaps and defects.
  • high resolution image construction of the as-built and idealized images may support defect detections at finer and configurable granularities, and may also allow for adaptation of physical additive manufacturing parameters to more efficiently and effectively manufacture parts.
  • image-based defect detection features described herein support parallelized rendering of hatch tracking using multi-threaded implements on CPUs or GPUs, and may thus support defect detections with increased speed and efficiency.
  • image-based defect detection features described herein may be implemented via various technical features that provide various technical benefits and results.
  • Figure 3 shows an example of logic 300 that a system may implement to support image-based defect detections in additive manufacturing.
  • the computing system 100 may implement the logic 300 as hardware, executable instructions stored on a machine-readable medium, or as a combination of both.
  • the computing system 100 may implement the logic 300 via the access engine 108 and the defect detection engine 110, through which the computing system 100 may perform or execute the logic 300 as a method to support image-based defect detections in additive manufacturing.
  • the following description of the logic 300 is provided using the access engine 108 and the defect detection engine 110 as examples. However, various other implementation options by systems are possible.
  • the access engine 108 accesses a slice contour of a given layer of a 3D object designed for manufacture through an additive manufacturing process (302) as well as obtain hatch tracking for the slice contour, the hatch tracking representative of an energy path to melt metal powder for constructing the given layer through the additive manufacturing process (304).
  • the defect detection engine 110 constructs, from the slice contour, an as-built image for the given layer by rendering the hatch tracking in the slice contour (306) as well as construct, from the slice contour, an idealized image for the given layer (308).
  • the defect detection engine 110 further identifies defects in the given layer via image analysis between the as-built image and the idealized image (310).
  • Figure 4 shows another example of logic 400 that a system may implement to support image-based defect detections in additive manufacturing.
  • the computing system 100 may implement the logic 400 as hardware, executable instructions stored on a machine-readable medium, or as a combination of both.
  • the computing system 100 may implement the logic 400 via the access engine 108 and the defect detection engine 110, through which the computing system 100 may perform or execute the logic 400 as a method to support image-based defect detections in additive manufacturing.
  • the following description of the logic 400 is provided using the access engine 108 and the defect detection engine 110 as examples. However, various other implementation options by systems are possible.
  • the access engine 108 accesses a 3D object model (which may be any 3D part geometry) and initialize a layer variable 'i' (402).
  • the layer variable 'i' may track a current layer of the 3D object model being analyzed for defect detection.
  • the access engine 108 may also create a slice contour of the 3D object model at layer 'i' (404). To do so, the access engine 108 may implement any number of build processor or CAM capabilities to slice a 3D geometry into layers for construction via additive manufacturing.
  • the slice contour may represent part boundaries for construction of layer 'i' of 3D object model, and the access engine 108 may determine hatch tracking via the slice contour at layer 'i' (406).
  • the access engine 108 may compute the hatch tracking via any number of CAM or build processor capabilities.
  • the defect detection engine 110 constructs an as-built image for layer 'i' by rendering the hatch tracking for layer 'i' (408), and doing so in any of the ways described herein.
  • the defect detection engine 110 renders multiple as-built images for layer 'i', e.g., different as-built images rendered using different color widths based on different melt pool width parameters.
  • the defect detection engine 110 constructs an as-built image for layer 'i' accounting for 'k' number of additional layers physically constructed on top of (e.g., above) layer 'i'.
  • the defect detection engine 110 also constructs an idealized image for layer 'i' by flood filling the slice contour for layer 'i' (410). Then, the defect detection engine 110 identifies defects in layer 'i' via image analysis between the as-built image(s) and the idealized image (412). In some implementations, the defect detection engine 110 may determine whether the defects identified in layer 'i' are significant (414), e.g., as measured according to a significance factor.
  • the significance factor may specify a threshold deficiency % in layer 'i' (e.g., greater than 5%), a threshold gap number (e.g., more than 100 gaps), a threshold maximum, minimum, or average gap size (e.g., 200 square micrometers), or any other configurable value by which the defect detection engine 110 may assess defect significance.
  • a threshold deficiency % in layer 'i' e.g., greater than 5%
  • a threshold gap number e.g., more than 100 gaps
  • a threshold maximum, minimum, or average gap size e.g. 200 square micrometers
  • the defect detection engine 110 may reduce resource consumption and increase analysis efficiency by providing a capability to stop a defect detection process upon identification of significant defects at a given layer 'i'. Responsive to determination that identified defects are sufficiently significant, the defect detection engine 110 may present a defect report (416), which may include any of the computed gap or defect statistics and/or highlight the significant defects identified for the layer. As noted above, the defect detection engine 110 may stop the defect detection process as well, conserving computation resources without (unnecessarily) performing defect detections for additional layers of a 3D geometry.
  • the defect detection engine 110 may determine whether additional layers remain in the 3D object model to process (418). If not, the defect detection engine 110 may increment the value of 'i' (420) and continue the defect detection process for the next layer in the 3D object model.
  • the logic 300 and 400 shown in Figures 3 and 4 provide illustrative examples by which a computing system 100 may support image-based defect detections in additive manufacturing. Additional or alternative steps in the logic 300 or 400 are contemplated herein, including according to any features described herein for the access engine 108, defect detection engine 110, or any combinations thereof.
  • FIG. 5 shows an example of a computing system 500 that supports image-based defect detections in additive manufacturing.
  • the computing system 500 may include a processor 510, which may take the form of a single or multiple processors.
  • the processor(s) 510 may include a central processing unit (CPU), microprocessor, or any hardware device suitable for executing instructions stored on a machine-readable medium.
  • the system 500 may include a machine-readable medium 520.
  • the machine-readable medium 520 may take the form of any non-transitory electronic, magnetic, optical, or other physical storage device that stores executable instructions, such as the access instructions 522 and the defect detection instructions 524 shown in Figure 5 .
  • the machine-readable medium 520 may be, for example, Random Access Memory (RAM) such as a dynamic RAM (DRAM), flash memory, spin-transfer torque memory, an Electrically-Erasable Programmable Read-Only Memory (EEPROM), a storage drive, an optical disk, and the like.
  • RAM Random Access Memory
  • DRAM dynamic RAM
  • EEPROM Electrically-Erasable Programmable Read-Only Memory
  • storage drive an optical disk, and the like.
  • the computing system 500 may execute instructions stored on the machine-readable medium 520 through the processor 510. Executing the instructions (e.g., the access instructions 522 and/or the defect detection instructions 524) may cause the computing system 500 to perform any of the image-based defect detection features described herein, including according to any of the features with respect to the access engine 108, the defect detection engine 110, or a combination of both.
  • execution of the access instructions 522 by the processor 510 may cause the computing system 500 to access a slice contour of a given layer of a 3D object designed for manufacture through an additive manufacturing process and obtain hatch tracking for the slice contour, the hatch tracking representative of an energy path to melt metal powder for constructing the given layer through the additive manufacturing process.
  • Execution of the defect detection instructions 524 by the processor 510 may cause the computing system 500 to construct, from the slice contour, an as-built image for the given layer by rendering the hatch tracking in the slice contour; construct, from the slice contour, an idealized image for the given layer; and identify defects in the given layer via image analysis between the as-built image and the idealized image.
  • the systems, methods, devices, and logic described above, including the access engine 108 and the defect detection engine 110, may be implemented in many different ways in many different combinations of hardware, logic, circuitry, and executable instructions stored on a machine-readable medium.
  • the access engine 108, the defect detection engine 110, or combinations thereof may include circuitry in a controller, a microprocessor, or an application specific integrated circuit (ASIC), or may be implemented with discrete logic or components, or a combination of other types of analog or digital circuitry, combined on a single integrated circuit or distributed among multiple integrated circuits.
  • ASIC application specific integrated circuit
  • a product such as a computer program product, may include a storage medium and machine-readable instructions stored on the medium, which when executed in an endpoint, computer system, or other device, cause the device to perform operations according to any of the description above, including according to any features of the access engine 108, the defect detection engine 110, or combinations thereof.
  • the processing capability of the systems, devices, and engines described herein, including the access engine 108 and the defect detection engine 110, may be distributed among multiple system components, such as among multiple processors and memories, optionally including multiple distributed processing systems or cloud/network elements.
  • Parameters, databases, and other data structures may be separately stored and managed, may be incorporated into a single memory or database, may be logically and physically organized in many different ways, and may be implemented in many ways, including data structures such as linked lists, hash tables, or implicit storage mechanisms.
  • Programs may be parts (e.g., subroutines) of a single program, separate programs, distributed across several memories and processors, or implemented in many different ways, such as in a library (e.g., a shared library).

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Materials Engineering (AREA)
  • Manufacturing & Machinery (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Mechanical Engineering (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Analytical Chemistry (AREA)

Claims (15)

  1. Computerimplementiertes Verfahren, umfassend:
    Zugreifen (302) auf eine Schnittkontur (231) einer vorgegebenen Schicht eines 3-dimensionalen (3D) Objektmodells (210), das zur Herstellung durch einen additiven Herstellungsprozess konstruiert wird;
    Erhalten (304) einer Schraffurverfolgung (232) für die Schnittkontur (231), wobei die Schraffurverfolgung (232) einen energiebasierten Pfad zum Schmelzen von Metallpulver zum Erstellen der vorgegebenen Schicht durch den additiven Herstellungsprozess darstellt;
    Erstellen (306), aus der Schnittkontur (231), eines Ist-Bildes (240) für die vorgegebene Schicht durch Rendern der Schraffurverfolgung (232) in der Schnittkontur (231);
    Erstellen (308), aus der Schnittkontur (231), eines idealisierten Bildes (250) durch vollständiges Einfärben des Inneren der Schnittkontur, um einen idealen Aufbau der vorgegebenen Schicht darzustellen; und
    Identifizieren (310) von Defekten in der vorgegebenen Schicht über eine Bildanalyse zwischen dem Ist-Bild (240) und dem idealisierten Bild (250).
  2. Verfahren nach Anspruch 1, wobei das Erstellen des Ist-Bildes (240) für die vorgegebene Schicht ferner Bestimmen einer Bildauflösung für das Ist-Bild (240), so dass eine Schwellengröße eines Spaltdefekts in der vorgegebenen Schicht durch eine Schwellenpixelbreite visualisiert wird, umfasst.
  3. Verfahren nach Anspruch 1, wobei das Erstellen des Ist-Bildes (240) für die vorgegebene Schicht Rendern der Schraffurverfolgung (232) mit einer variablen Farbbreite gemäß einer statistischen Funktion, die eine Schmelzbadbreite des additiven Herstellungsprozesses modelliert, zumindest basierend auf einer Laserleistung, einer Lasergeschwindigkeit und Metallpulvereigenschaften umfasst.
  4. Verfahren nach Anspruch 1, wobei das Erstellen des Ist-Bildes (240) für die vorgegebene Schicht Rendern der Schraffurverfolgung (232) mit einer konstanten Farbbreite wie durch einen Schmelzbadbreitenparameter für den additiven Herstellungsprozess spezifiziert umfasst.
  5. Verfahren nach Anspruch 4, wobei das Erstellen des Ist-Bildes (240) für die vorgegebene Schicht ferner Bestimmen einer Bildauflösung für das Ist-Bild (240) basierend auf einer vorgegebenen Pixelbreite für den Schmelzbadbreitenparameter umfasst.
  6. Verfahren nach Anspruch 1, wobei das Erstellen des idealisierten Bildes (250) für die vorgegebene Schicht Flutfüllen der Schnittkontur (231) für die vorgegebene Schicht umfasst.
  7. Verfahren nach Anspruch 1, wobei die Bildanalyse einen Bildunterschied zwischen dem Ist-Bild (240) und dem idealisierten Bild (250) umfasst.
  8. System (100), umfassend:
    eine Zugriffs-Engine (108), die zu Folgendem ausgelegt ist:
    Zugreifen auf eine Schnittkontur (231) einer vorgegebenen Schicht eines 3-dimensionalen (3D) Objektmodells (210), das zur Herstellung durch einen additiven Herstellungsprozess konstruiert ist; und
    Erhalten einer Schraffurverfolgung (232) für die Schnittkontur (231), wobei die Schraffurverfolgung (232) einen Energiepfad zum Schmelzen von Metallpulver zum Aufbauen der vorgegebenen Schicht durch den additiven Herstellungsprozess darstellt; und
    eine physische Detektions-Engine (110), die zu Folgendem ausgelegt ist:
    Erstellen, aus der Schnittkontur (231), eines Ist-Bildes (240) für die vorgegebene Schicht durch Rendern der Schraffurverfolgung (232) in der Schnittkontur (231);
    Erstellen, aus der Schnittkontur (231), eines idealisierten Bildes (250) durch vollständiges Einfärben des Inneren der Schnittkontur, um einen idealen Aufbau der vorgegebenen Schicht darzustellen; und
    Identifizieren von Defekten in der vorgegebenen Schicht über eine Bildanalyse zwischen dem Ist-Bild (240) und dem idealisierten Bild (250).
  9. System nach Anspruch 8, wobei die Defektdetektions-Engine (110) zum Erstellen des Ist-Bildes (240) für die vorgegebene Schicht ferner durch Bestimmen einer Bildauflösung für das Ist-Bild (240), so dass eine Schwellengröße eines Spaltdefekts in der vorgegebenen Schicht durch eine Schwellenpixelbreite visualisiert wird, ausgelegt ist.
  10. System nach Anspruch 8, wobei die Defektdetektions-Engine (110) zum Erstellen des Ist-Bildes (240) für die vorgegebene Schicht durch Rendern der Schraffurverfolgung (232) mit einer variablen Farbbreite gemäß einer statistischen Funktion, die eine Schmelzbadbreite des additiven Herstellungsprozesses modelliert, zumindest basierend auf einer Laserleistung, einer Lasergeschwindigkeit und Metallpulvereigenschaften ausgelegt ist.
  11. System nach Anspruch 8, wobei die Defektdetektions-Engine (110) zum Erstellen des Ist-Bildes (240) für die vorgegebene Schicht durch Rendern der Schraffurverfolgung (232) mit einer konstanten Farbbreite wie durch einen Schmelzbadbreitenparameter für den additiven Herstellungsprozess spezifiziert ausgelegt ist.
  12. System nach Anspruch 11, wobei die Defektdetektions-Engine (110) zum Erstellen des Ist-Bildes (240) für die vorgegebene Schicht ferner durch Bestimmen einer Bildauflösung für das Ist-Bild (240) basierend auf einer vorgegebenen Pixelbreite für den Schmelzbadbreitenparameter ausgelegt ist.
  13. System nach Anspruch 8, wobei die Defektdetektions-Engine (110) zum Erstellen des idealisierten Bildes (250) für die vorgegebene Schicht durch Flutfüllen der Schnittkontur (231) für die vorgegebene Schicht ausgelegt ist.
  14. System nach Anspruch 8, wobei die Bildanalyse einen Bildunterschied zwischen dem Ist-Bild (240) und dem idealisierten Bild (250) umfasst.
  15. Nicht-flüchtiges maschinenlesbares Medium (520), das Anweisungen (522, 524) umfasst, die, wenn sie von einem Prozessor (510) ausgeführt werden, ein Rechensystem (500) zu Folgendem veranlassen:
    Zugreifen auf eine Schnittkontur (231) einer vorgegebenen Schicht eines 3-dimensionalen (3D) Objektmodells (210), das zur Herstellung durch einen additiven Herstellungsprozess konstruiert ist;
    Erhalten einer Schraffurverfolgung (232) für die Schnittkontur (231), wobei die Schraffurverfolgung (232) einen Energiepfad zum Schmelzen von Metallpulver zum Aufbauen der vorgegebenen Schicht durch den additiven Herstellungsprozess darstellt;
    Erstellen, aus der Schnittkontur (231), eines Ist-Bildes (240) für die vorgegebene Schicht durch Rendern der Schraffurverfolgung (232) in der Schnittkontur (231);
    Erstellen, aus der Schnittkontur (231), eines idealisierten Bildes (250) durch vollständiges Einfärben des Inneren der Schnittkontur, um einen idealen Aufbau der vorgegebenen Schicht darzustellen; und
    Identifizieren von Defekten in der vorgegebenen Schicht über eine Bildanalyse zwischen dem Ist-Bild (240) und dem idealisierten Bild (250).
EP19758533.4A 2019-07-25 2019-07-25 Bildbasierte fehlerdetektionen in der generativen fertigung Active EP3987480B1 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/US2019/043411 WO2021015782A1 (en) 2019-07-25 2019-07-25 Image-based defect detections in additive manufacturing

Publications (3)

Publication Number Publication Date
EP3987480A1 EP3987480A1 (de) 2022-04-27
EP3987480B1 true EP3987480B1 (de) 2025-09-24
EP3987480C0 EP3987480C0 (de) 2025-09-24

Family

ID=67734797

Family Applications (1)

Application Number Title Priority Date Filing Date
EP19758533.4A Active EP3987480B1 (de) 2019-07-25 2019-07-25 Bildbasierte fehlerdetektionen in der generativen fertigung

Country Status (4)

Country Link
US (1) US12159390B2 (de)
EP (1) EP3987480B1 (de)
CN (1) CN114175092A (de)
WO (1) WO2021015782A1 (de)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021021153A1 (en) * 2019-07-31 2021-02-04 Hewlett-Packard Development Company, L.P. Generating thermal images
US11537111B2 (en) * 2020-04-01 2022-12-27 General Electric Company Methods and apparatus for 2-D and 3-D scanning path visualization
CN113909630B (zh) * 2021-09-29 2022-07-26 南京英尼格玛工业自动化技术有限公司 一种加强筋金属结构件分区打印填充的电弧增材制造方法
CN114273671B (zh) * 2021-12-13 2024-11-29 南京理工大学 一种双光束激光粉末床熔融模拟仿真方法
CN114549497B (zh) * 2022-02-28 2022-11-29 扬州市恒邦机械制造有限公司 基于图像识别的走台板表面缺陷检测方法及人工智能系统
CN119017694A (zh) * 2022-03-28 2024-11-26 深圳市纵维立方科技有限公司 3d打印方法、装置、存储介质及计算机设备
CN116442528A (zh) * 2023-05-31 2023-07-18 南京铖联激光科技有限公司 一种基于图形识别的零件切片的定位方法
CN117593302B (zh) * 2024-01-18 2024-05-24 新西旺智能科技(深圳)有限公司 一种缺陷零件溯源方法及系统
CN118371734B (zh) * 2024-06-24 2024-08-23 临沂大学 基于深度学习的增材制造缺陷检测系统及方法
CN119772210B (zh) * 2024-12-26 2026-04-10 北京航星机器制造有限公司 一种增材制造成形过程检测方法和铝合金零件
CN119600023B (zh) * 2025-02-10 2025-06-10 广州安特激光技术有限公司 用于选择性激光溶化3d打印的实时缺陷检测方法及系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10719929B2 (en) * 2015-11-16 2020-07-21 Materialise N.V. Error detection in additive manufacturing processes
WO2017141070A1 (en) * 2016-02-16 2017-08-24 Phatak Amar Method and system for rapid prototyping via virtual simulation
CN108197384B (zh) * 2017-12-30 2021-11-02 大族激光科技产业集团股份有限公司 粉末激光3d打印成型工艺的参数优化方法
CN109128824A (zh) 2018-04-28 2019-01-04 山东雷石智能制造股份有限公司 一种基于动态参数调整的增减材一体的五轴混合加工设备及加工方法
CN108760747B (zh) * 2018-04-28 2019-12-10 浙江大学 一种3d打印模型表面缺陷视觉检测方法

Also Published As

Publication number Publication date
CN114175092A (zh) 2022-03-11
US20220270236A1 (en) 2022-08-25
EP3987480C0 (de) 2025-09-24
WO2021015782A1 (en) 2021-01-28
US12159390B2 (en) 2024-12-03
EP3987480A1 (de) 2022-04-27

Similar Documents

Publication Publication Date Title
US12159390B2 (en) Image-based defect detections in additive manufacturing
US12491590B2 (en) Method for repairing workpiece involves using requirement information to check whether simulated physical behavior fulfills requirement
Lin et al. Online quality monitoring in material extrusion additive manufacturing processes based on laser scanning technology
JP7023939B2 (ja) 付加製造環境におけるエネルギー密度マッピング
US11155034B2 (en) System and method for distortion mitigation and compensation in additive manufacturing processes through B-spline hyperpatch field
US20230302539A1 (en) Tool for scan path visualization and defect distribution prediction
US11733678B2 (en) Method for determining building instructions for an additive manufacturing method, method for generating a database with correction measures for controlling the process of an additive manufacturing method
CN114101707B (zh) 激光增材制造功率控制方法、系统、介质及电子设备
JP2018538167A (ja) 積層造形プロセスにおけるエラー検出
US20190118480A1 (en) Generating additive manufacturing instructions
Vaidya et al. Image processing assisted tools for pre-and post-processing operations in additive manufacturing
Zhao et al. Region-based online flaw detection of 3D printing via fringe projection
US20200272128A1 (en) Sensor based smart segmentation
KR20200007892A (ko) 속성값 시프트를 보상하기 위한 속성 데이터 변환
Taufik et al. Computer aided visualization tool for part quality analysis of additive manufacturing process
US20210201562A1 (en) Transforming object data models to disperse object properties
US20210200185A1 (en) Determining object volumes in virtual object space
CN117291909B (zh) 一种发光二极管生产设备的智能控制方法及系统
US20230032439A1 (en) Generation of an object model for three dimensional printers
EP3616885A1 (de) Dreidimensionales druckverfahren und dreidimensionale druckvorrichtung
US20250021721A1 (en) Lattice structure thicknesses
JP2024050514A (ja) フィレット検出方法
Wu et al. Five-axis support-free adaptive slicing optimization for STL model detail features
CN115769212B (zh) 用于物理零件的3d打印的热量感知工具路径生成
Janik The method of a material loss detection for cylindrical shape parts of elements with a 3D scanning application

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20220121

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20250203

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

INTG Intention to grant announced

Effective date: 20250425

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602019076116

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

U01 Request for unitary effect filed

Effective date: 20251002

U07 Unitary effect registered

Designated state(s): AT BE BG DE DK EE FI FR IT LT LU LV MT NL PT RO SE SI

Effective date: 20251014

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20251224

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20250924

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20251225

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20251224

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20250924

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20250924

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20260124

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20250924

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20250924

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20250924